© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7901
    Prev
    Next
    INDEX
    Explanations

    contaminants or issues related to drinking water

    oai_token-act-pair · gpt-3.5-turbo

    references to drinking water or beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sharif
    -0.78
    theless
    -0.73
    ural
    -0.69
    eele
    -0.67
    SEC
    -0.66
     notch
    -0.66
    moving
    -0.64
    asia
    -0.63
    locked
    -0.62
    pora
    -0.62
    POSITIVE LOGITS
     alcohol
    1.02
    water
    0.97
    cohol
    0.96
     bottles
    0.96
     water
    0.96
     gallons
    0.94
     drinking
    0.93
     beverages
    0.89
     soda
    0.88
    bott
    0.87
    Activations Density 0.032%

    No Known Activations